Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantities related to measurable concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ī
    -0.17
    iten
    -0.16
     gallons
    -0.15
    pagen
    -0.14
    pars
    -0.14
    NavItem
    -0.14
    adt
    -0.14
    -mile
    -0.14
    Ä°L
    -0.14
     éĢ
    -0.13
    POSITIVE LOGITS
     bis
    0.20
    bis
    0.18
    eron
    0.16
     Bis
    0.16
     Banc
    0.15
     Pu
    0.15
    опÑĢоÑģ
    0.14
    sen
    0.14
    smith
    0.14
    HEMA
    0.14
    Act Density 0.190%

    No Known Activations